Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1381 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0161. Min Range: -5.0161
Max Act: 5.0161. Min Act: -0.1700
Data Index: 2076025 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0161. Min Range: -5.0161
Max Act: 5.0161. Min Act: -0.1700
Data Index: 3631723 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.9536. Min Act: -0.1700
Data Index: 7509599 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 4600141 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8286. Min Act: -0.1700
Data Index: 3233942 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8286. Min Act: -0.1700
Data Index: 7544003 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7974. Min Act: -0.1700
Data Index: 7700143 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7974. Min Act: -0.1700
Data Index: 6179615 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7661. Min Act: -0.1700
Data Index: 7193606 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7349. Min Act: -0.1700
Data Index: 7523941 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7349. Min Act: -0.1700
Data Index: 6105327 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 3947764 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7661. Min Act: -0.1700
Data Index: 8120200 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7349. Min Act: -0.1700
Data Index: 4640322 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 855515 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 7982907 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 3446823 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5216537 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6411. Min Act: -0.1700
Data Index: 666852 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6411. Min Act: -0.1700
Data Index: 5150472 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19